CN106603999A - Video monitoring alarming method and system - Google Patents
Video monitoring alarming method and system Download PDFInfo
- Publication number
- CN106603999A CN106603999A CN201710087254.5A CN201710087254A CN106603999A CN 106603999 A CN106603999 A CN 106603999A CN 201710087254 A CN201710087254 A CN 201710087254A CN 106603999 A CN106603999 A CN 106603999A
- Authority
- CN
- China
- Prior art keywords
- video
- content
- moving object
- suspicious
- warning message
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Closed-Circuit Television Systems (AREA)
- Alarm Systems (AREA)
Abstract
The present invention provides a video monitoring alarming method and system to solve a problem that a monitoring user needs to watch a video to know the content of an alarm in the prior art. Specifically, an artificial intelligence method is used to carry out information extraction of the content of an alarm video, the video content is converted into key points which the monitoring user can rapidly obtain and comprehensible content of texts, pictures, voices and the like, thus the user does not need to download and watch the whole video to know the main content of monitoring video information, the time of the user is saved, and the efficiency of obtaining the information is improved.
Description
Technical field
The application is related to field of video monitoring, specially a kind of video monitoring alarm method and system.
Background technology
Video monitoring is the important component part of safety and protection system, is a kind of stronger integrated system of prevention ability.Mesh
Before, with developing rapidly and scientific and technical progress for social economy, video monitoring system is directly perceived, accurate, timely and interior with which
Hold abundant and be widely used in many occasions, but the scale application of video monitoring causes and goes to distinguish by human factorss and be difficult
Accomplish perfectly safe.The application developed rapidly as video monitoring of computer technology provides bigger display stage, intelligent
Field is taken precautions against in security also more and more to be applied.
Warning video information simply can only be sent to monitoring user by existing Video Surveillance Alarm System, and user is necessary
The particular content of alarm is will appreciate that after checking video, such shortcoming is detrimental to monitoring user and quickly obtains warning message,
If the scope of video monitoring is larger, monitoring user may need using the substantial amounts of time to check video, may miss weight
Want information.Meanwhile, in the fast-developing modern society of mobile Internet, monitoring user widely uses mobile phone as alert receipt
End, not can immediately know that due to transmission of video very consumption of network resources and alert content, and most users are intended to energy
There is the method for simple knowledge video monitoring alert content quickly to process to alarm.
Application content
The purpose of the application is to provide the method and system that a kind of video monitoring is reported to the police, for solving to monitor under prior art
User must look at the problem that video just can know that alert content, so as to realize that quickly understanding warning information and fast alarms rings
Should.
According to the one side of the application, there is provided a kind of method that video monitoring is reported to the police, the method include:Obtain video
Content;When suspicious content is included in the video content, export warning message, wherein, the warning message is included with regard to institute
State the summary info of suspicious content.
Further, when including suspicious content in the video content, the method for exporting warning message is included to video
Content moves detecting, extracts the suspicious frame comprising moving object, generates further according to the suspicious frame comprising moving object
And export warning message.
Further, it is right that the method for generating and exporting warning message according to the suspicious frame comprising moving object includes
Moving object in the suspicious frame carries out object identification, obtains the recognition result of the moving object, then according to the fortune
The recognition result of animal body determines the summary info with regard to the suspicious content, believes further according to the summary with regard to the suspicious content
Breath is generated and exports warning message.
Yet further, the method that the moving object in the suspicious frame carries out object identification is included to comprising easy flase drop
Filtered in the suspicious frame of content, obtain filter after suspicious frame, then to filtration after suspicious frame in moving object enter
Row object identification.
Yet further, the easy flase drop content includes the image change content caused by light change and by predetermined movement
The image change content that object causes.
Yet further, the method that the moving object in the suspicious frame carries out object identification is included using default thing
Body Model, carries out object identification to the moving object in the suspicious frame.
Further, detecting is moved to video content, the method for extracting the suspicious frame comprising moving object includes
The multiple successive image frames in video content are read, then multiple successive image frames are carried out with the comparing calculation of interframe, extract bag
Suspicious frame containing moving object.
Further, the output warning message includes exporting the warning message of presets, wherein, the presets
Including following any one or more of combination:Word, picture, voice and video.
Further, the summary info with regard to the suspicious content includes the title of moving object, moving object
The sectional drawing of time of occurrence, the sports immunology of moving object and moving object.
According to the another aspect of the application, a kind of Video Surveillance Alarm System is additionally provided, the system includes that video is adopted
Collection equipment and analysis warning device, video capture device are used to obtain video content;Analysis warning device, in the video
When suspicious content is included in content, export warning message, wherein, the warning message includes the summary with regard to the suspicious content
Information.
Further, the analysis warning device, including extraction element and alarm device, extraction element is in video
Appearance moves detecting, extracts the suspicious frame comprising moving object;Alarm device for according to it is described comprising moving object can
Doubtful frame is generated and exports warning message.
Further, the alarm device, including identification module, summary info determining module and warning message generate defeated
Go out module, identification module obtains the knowledge of the moving object for object identification is carried out to the moving object in the suspicious frame
Other result;Summary info determining module is for according to the recognition result of moving object determination plucking with regard to the suspicious content
Want information;Warning message generates output module to be used to generate and export alarm signal according to the summary info with regard to the suspicious content
Breath.
Yet further, the identification module was obtained for filtering in the suspicious frame to including easy flase drop content
Suspicious frame after filter and to the filtration after suspicious frame in moving object carry out object identification.
Yet further, the easy flase drop content includes the image change content caused by light change and by predetermined movement
The image change content that object causes.
Yet further, the identification module is used for using default object model, to the moving object in the suspicious frame
Body carries out object identification.
Further, the extraction element is used to read multiple successive image frames in video content and to multiple continuous
Picture frame carries out the comparing calculation of interframe, extracts the suspicious frame comprising moving object.
Further, the warning message generates output module and is used to export the warning message of presets, wherein, it is described
Presets include following any one or more of combination:Word, picture, voice and video.
Further, the summary info with regard to the suspicious content includes the title of moving object, moving object
The sectional drawing of time of occurrence, the sports immunology of moving object and moving object.
Compared with prior art, the technical scheme of the application is carried out to warning video content using the method for artificial intelligence
Information abstraction, by video content be converted into convenient monitoring user can quickly obtain main points and understandable word, picture,
The contents such as voice so that user need not download the main contents that whole section of video of viewing can just know monitoring video information, section
User time has been saved, information acquisition efficiency has been improve.
Description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application other
Feature, objects and advantages will become more apparent upon:
The flow chart of the video monitoring alarm method that Fig. 1 is provided for the embodiment of the present application;
The structural representation of the Video Surveillance Alarm System that Fig. 2 is provided for the embodiment of the present application;
The structural representation of the preferred video monitoring and alarming system that Fig. 3 is provided for the embodiment of the present application;
The functional flow diagram of the preferred video monitoring and alarming system that Fig. 4 is provided for the embodiment of the present application;
The video analysis flow chart of the preferred video monitoring and alarming system that Fig. 5 is provided for the embodiment of the present application;
The warning message sample figure of the preferred video monitoring and alarming system that Fig. 6 is provided for the embodiment of the present application;
In accompanying drawing, same or analogous reference represents same or analogous part.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present application, the technical scheme in the embodiment of the present application is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only some embodiments of the present application, rather than the embodiment of whole.It is based on
Embodiment in the application, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of the application protection.
Fig. 1 shows a kind of video monitoring alarm method that the embodiment of the present application is provided, and the method includes following several steps
Suddenly:
Step S101, obtains video content;
Step S102, when including suspicious content in the video content, exports warning message, wherein, the alarm signal
Breath includes the summary info with regard to the suspicious content.
Here, be usually used in step S101 to possess the equipment of video acquisition function to obtain video content, these equipment
There are photographic head, video camera etc..Ordinary video collecting device do not possess the detection function to object of which movement, and some expanded functions are regarded
Frequency collecting device can carry out simple moving object segmentation, realize that preliminary object of which movement judges.
The suspicious content occurs in that moving object in referring to monitor video, and some moving objects such as people may be to working as
The environment of front monitoring causes potential threat, needs monitoring personnel to be confirmed to ensure safety to these suspicious contents.
When step S102 includes suspicious content in the video content, the method for exporting warning message is specifically included:
First, detecting is moved to video content, the suspicious frame comprising moving object is extracted;
Video is made up of multiple continuous picture frames, and in video, the athletic performance of object occurs in consecutive image for the object
Diverse location in frame, existing Video content analysis technique are by detecting the change in location of object model in video finding out
With the presence or absence of the object of motion.
Detecting is moved to video content, including the multiple successive image frames read in video content, then to multiple
Successive image frame carries out the comparing calculation of interframe, extracts the suspicious frame comprising moving object.
After mobile detection, the picture frame for not having object of which movement is removed original video content, only remaining to include
There is the i.e. suspicious frame of those picture frames of moving object, as the input data of next step object identification.
2nd, warning message is generated and export according to the suspicious frame comprising moving object, specifically include;
1) object identification is carried out to the moving object in the suspicious frame, the recognition result of the moving object is obtained;
The method that object identification is carried out to the moving object in the suspicious frame, including to suspicious comprising easy flase drop content
Filtered in frame, obtain filter after suspicious frame, then to filtration after suspicious frame in moving object carry out object identification.
The image change that the easy flase drop content includes the image change content caused by light change and caused by predetermined movement object
Content.
After detecting is moved to video content, the suspicious frame that obtains can not directly carry out the identification of moving object, this be because
It is the presence of the movable interference factor of non-human in monitoring scene, the change of such as time morning and evening or weather can cause background illumination
Change, activity etc. of non-human organism such as the object such as cat, Canis familiaris L., winged mosquito in monitoring scene, i.e., described easy flase drop content, if not pre-
These influence factors are first excluded, the object recognition algorithm in later stage can be interfered so that the accuracy of object identification declines,
Cause erroneous judgement.
The method that object identification is carried out to the moving object in the suspicious frame, is also included using default object model,
Object identification is carried out to the moving object in the suspicious frame.
Object in suspicious frame is identified needing the method using pattern recognition.If in video monitoring to be identified
The polytype object being likely to occur, such as people, Canis familiaris L., cat, door etc., needs are first modeled to these objects, by substantial amounts of
Training material is trained to model so that model can be accurately judged to these objects.In general, the object in video monitoring
Identification needs nearly thousand kinds of common object models are recognized accurately.
2) summary info with regard to the suspicious content is determined according to the recognition result of the moving object;
After being identified to the object in suspicious frame by using pattern recognition engine, the knowledge of one or more objects is produced
Other result, different according to the level of detail of object identification function, recognition result describes object using various different attributes, this
Summary info in application embodiment with regard to the suspicious content has used a part of attribute of object identification result, at least includes
The sectional drawing of the title of moving object, the time of occurrence of moving object, the sports immunology of moving object and moving object these identification
Attribute.
3) generate and export warning message according to the summary info with regard to the suspicious content.
The form of the warning message provided in the embodiment of the present application has various, and monitoring user can be set according to the needs of oneself
Put the message form of preference, such as combination in any of word, picture, voice, video or more form etc..
According to the another aspect of the application, a kind of Video Surveillance Alarm System, structure such as Fig. 2 institutes of the system are additionally provided
Show, including video capture device 210 and analysis warning device 220.Specifically, video capture device 210 is used to obtain in video
Hold;When analysis warning device 220 is for including suspicious content in the video content, warning message is exported, wherein, the report
Alarming information includes the summary info with regard to the suspicious content.
Here, video capture device 210 typically possesses the equipment of video acquisition function, these equipment have photographic head, take the photograph
Camera etc..Ordinary video collecting device does not possess the detection function to object of which movement, the video capture device of some expanded functions
Simple moving object segmentation can be carried out, realizes that preliminary object of which movement judges.
The suspicious content occurs in that moving object in referring to monitor video, and some moving objects such as people may be to working as
The environment of front monitoring causes potential threat, needs monitoring personnel to be confirmed to ensure safety to these suspicious contents.
When analysis warning device 220 is for including suspicious content in the video content, warning message is exported, it is concrete to wrap
Include:
First, extraction element 310, for detecting is moved to video content, extract the suspicious frame comprising moving object;
Video is made up of multiple continuous picture frames, and in video, the athletic performance of object occurs in consecutive image for the object
Diverse location in frame, existing Video content analysis technique are by detecting the change in location of object model in video finding out
With the presence or absence of the object of motion.
Detecting is moved to video content, including the multiple successive image frames read in video content, then to multiple
Successive image frame carries out the comparing calculation of interframe, extracts the suspicious frame comprising moving object.
After mobile detection, the picture frame for not having object of which movement is removed original video content, only remaining to include
There is the i.e. suspicious frame of those picture frames of moving object, as the input data of next step object identification.
2nd, alarm device 320, for generating and exporting warning message according to the suspicious frame comprising moving object, tool
Body includes;
1) identification module 410, for object identification is carried out to the moving object in the suspicious frame, obtain the moving object
The recognition result of body;
The method that object identification is carried out to the moving object in the suspicious frame, including to suspicious comprising easy flase drop content
Filtered in frame, obtain filter after suspicious frame, then to filtration after suspicious frame in moving object carry out object identification.
The image change that the easy flase drop content includes the image change content caused by light change and caused by predetermined movement object
Content.
After detecting is moved to video content, the suspicious frame that obtains can not directly carry out the identification of moving object, this be because
It is the presence of the movable interference factor of non-human in monitoring scene, the change of such as time morning and evening or weather can cause background illumination
Change, activity etc. of non-human organism such as the object such as cat, Canis familiaris L., winged mosquito in monitoring scene, i.e., described easy flase drop content, if not pre-
These influence factors are first excluded, the object recognition algorithm in later stage can be interfered so that the accuracy of object identification declines,
Cause erroneous judgement.
The method that object identification is carried out to the moving object in the suspicious frame, is also included using default object model,
Object identification is carried out to the moving object in the suspicious frame.
Object in suspicious frame is identified needing the method using pattern recognition.If in video monitoring to be identified
The polytype object being likely to occur, such as people, Canis familiaris L., cat, door etc., needs are first modeled to these objects, by substantial amounts of
Training material is trained to model so that model can be accurately judged to these objects.In general, the object in video monitoring
Identification needs nearly thousand kinds of common objects are recognized accurately.
2) summary info determining module 420, for being determined with regard to described suspicious according to the recognition result of the moving object
The summary info of content;
After being identified to the object in suspicious frame by using pattern recognition engine, the knowledge of one or more objects is produced
Other result, different according to the level of detail of object identification function, recognition result describes object using various different attributes, this
Summary info in application embodiment with regard to the suspicious content has used a part of attribute of object identification result, at least includes
The sectional drawing of the title of moving object, the time of occurrence of moving object, the sports immunology of moving object and moving object these identification
Attribute.
3) warning message generates output module 430, generates and defeated for summary info of the basis with regard to the suspicious content
Go out warning message.
The form of the warning message provided in the embodiment of the present application has various, and monitoring user can be set according to the needs of oneself
Put the message form of preference, such as combination in any of word, picture, voice, video or more form etc..
Further, the embodiment of the present application additionally provides a kind of preferred Video Surveillance Alarm System, the optimum decision system
Structure is as shown in figure 3, including monitoring device 1, cloud service cluster 2 and receiving device 3.
Video source of the monitoring device 1 as safety monitoring alarming, for monitoring current location, and the video that will be gathered
Content is sent to cloud service cluster 2.Monitoring device 1 is provided simultaneously with simple abnormity detecting warning function, is detecting abnormal feelings
Warning message can be sent to cloud service cluster 2 during condition.The white intelligent video camera head of rice wife and children used in the embodiment of the present application.
The cloud service cluster 2 is the Cloud Server group being erected on cloud computing platform, including Alarm Server 21, storage
Server 22 and Analysis server 23.
The monitoring device 1 realizes the function of video capture device 210, and cloud service cluster 2 realizes analysis warning device 220
Function.The Alarm Server 21 realizes summary info determining module and warning message generates the function of output module, described
Analysis server 23 realizes the function of extraction element and identification module in application scheme.The storage server 22 can be used
The mode and medium of any network storage, for storing the monitor video of video capture device upload, makes in the embodiment of the present application
Monitor video is preserved with Semen setariae FDS file storage services.
The major responsibility of the cloud service cluster 2 includes as follows:
1. data storage:The data that storage monitoring device 1 is uploaded, data type may be video, picture, voice etc..Collection
Group can also be encrypted to data, it is ensured that Information Security.
2. warning message is received:Receive the warning message of the transmission of monitoring device 1 and parsed, then get out alarm correspondence
Video content, submit to Analysis server 23 and processed.
3. video analysis:Video content to obtaining moves object detecting, and extraction has the suspicious figure of moving object
As frame, while the picture frame contents that motionless picture, winged mosquito, change of sunlight etc. may produce flase drop are filtered, finally
Image recognition is carried out to picture frame, the object of motion is identified.
4. result is generated:The recognition result of moving object is carried out simplifying process, generate people can with well-known content,
Such as word, picture or voice etc..
5. alarm sends:The alert content of generation is sent to into the receiving device 3 that monitoring device 1 is bound.
The receiving device 3 is used to receive warning message, and warning message can be video, picture and word, incidentally filter
The description of contents simplified afterwards.The push of warning message, receiving device 3 are realized in the embodiment of the present application based on wechat public platform
Need to pay close attention to default official's public number in wechat platform.
Need to install on the Analysis server 23 Java with C++ programming languages running environment and application server Tomcat
7, primary C++SO is called in Java language altogether using JNI (Java Native Interface, Java local interfaces) mechanism
Storehouse is enjoyed, the efficient process of video content on Analysis server 23 are realized.
The alarm information pushing function of the Alarm Server 21 is realized using Jersey webapi open source projects and integrated
Wechat public's development platform, warning message are pushed to receiving device 3 by wechat.
Fig. 4 shows the functional sequence of the preferred video monitoring and alarming system that the embodiment of the present application is provided, wherein, including such as
Lower step:
A) 1 unusual circumstance of monitoring device sends warning message to Alarm Server 21;
B) warning message is sent to processing server (i.e. Analysis server 22) by Alarm Server 21;
C) Analysis server 22 applies for video content to content server (i.e. storage server 23);
D) storage server 23 returns video content to Analysis server 22;
E) Analysis server 22 performs following steps:CPU detects video;GPU is to detecting content recognition;In after transmission processe
Hold;
F) Alarm Server 21 sends alarming result to receiving device 3.
1 executable flow process of the monitoring device includes normal acquisition flow process and alarm flow, and normal acquisition flow process includes
Following steps:
1. monitoring device 1 normally monitors and video is uploaded to Alarm Server 21 on time;
2. Alarm Server 21 preserves video to content server (i.e. storage server 23).
If the monitoring device 1 supports that detecting function, the alarm flow that can be performed comprise the steps:
1) analysis of monitoring device 1 live video stream, judges whether abnormal conditions;
2) if there is abnormal conditions, monitoring device 1 arranges warning message;If there is no abnormal conditions, monitoring device 1
Warning message is set for sky;
3) monitoring device 1 checks the warning message of generation, if warning message is sky, does not send warning message;Such as retribution
Alarming information is not sky, sends warning message to Alarm Server 21.
The flow process that the Alarm Server 21 is performed includes alarm analysis flow process and reports to the police pushing flow process, alarm analysis flow process
Comprise the steps:
1) Alarm Server 21 receives warning message;
2) parsing of Alarm Server 21 warning message;
3) Alarm Server 21 is searched according to warning message and obtains storage address of the warning video in storage server 22;
4) Alarm Server 21 sends video storage address to Analysis server 23.
The analysis process that the Analysis server 23 is performed comprises the steps:
1) Analysis server 23 receives the video storage address that Alarm Server 21 sends;
2) Analysis server 23 arranges video request information according to video storage address;
3) Analysis server 23 sends video request information to storage server 22;
4) Analysis server 23 receives the video file that storage server 22 is returned;
5) Analysis server 23 reads a series of successive image frames in video file;
6) Analysis server 23 carries out the comparing calculation of interframe to successive image frame, obtains the presence of a series of of moving object
Picture frame;
7) Analysis server 23 is filtered to the view data that flase drop is also easy to produce in image series frame, after being filtered
Picture frame;
8) picture frame after Analysis server 23 pairs is filtered carries out object identification, obtains object identification data;
9) Analysis server 23 is according to object identification data genaration analysis result;
10) analysis result is sent to Alarm Server 21 by Analysis server 23;
The warning that the Alarm Server 21 is performed pushes flow process and comprises the steps:
1) Alarm Server 21 receives the analysis result that Analysis server 23 sends;
2) Alarm Server 21 produces alarming result according to analysis result;
3) inquiry of Alarm Server 21 obtains the receiving device 3 of the binding of monitoring device 1;
4) Alarm Server 21 is sent to alarming result on receiving device 3.
Fig. 5 shows the video analysis flow process of the preferred video monitoring and alarming system that the embodiment of the present application is provided.The application
Used in embodiment, artificial intelligence engine Caffe is realizing object identification.Before video analysis are carried out, need first to prepare a large amount of
The training material such as object such as people, Canis familiaris L., cat, door model training is carried out to Caffe engines so that Caffe engines can be accurately identified
The model of each type objects, the Caffe engines after training can recognize nearly thousand kinds of common objects at present.
Detecing for moving object is carried out to the video being input into using Caffe built-in moving object segmentation algorithm during video analysis
The filtration with easy flase drop content is surveyed, the picture frame comprising moving object is obtained, these picture frames Caffe again by training before
Model is identified and is identified result.
In the processing module of Caffe engines, correlation function is performed using different processing units, for example, is used
CPU (Central Processing Unit, CPU) is captured and flase drop come the dynamic object for processing computation-intensive
Filtering function, performs criticizing for image procossing intensity using GPU (Graphics Processing Unit, Graphics Processing Unit)
Amount picture processing and picture object identification function, can effectively lift the efficiency of object identification by way of processing respectively.
Fig. 6 shows the warning message sample of the preferred video monitoring and alarming system that the embodiment of the present application is provided, including tactile
The time of sending out, triggering type and triggering details, wherein, the title comprising moving object in details is triggered, triggered time correspondence is moved
The time of occurrence of object, triggers the sports immunology of type correspondence moving object, clicks on " details " button and can obtain moving object
Sectional drawing and detailed video information.Warning message is sent on receiving device 3 and explanatory note after incidentally analyzing by network, no
Monitoring user is needed further to open content access, video can also be straight according to explanatory note if monitoring user wants access
Connect and choose time of fire alarming section and check.The embodiment of the present application is the wechat client that alarming result is pushed to monitoring user, is supervised
Control user can be directly viewable text and understand video content, check that sectional drawing and detailed alarm are regarded after can also clicking on " details " button
Frequently.
Compared with prior art, the technical scheme of the application is carried out to warning video content using the method for artificial intelligence
Information abstraction, by video content be converted into convenient monitoring user can quickly obtain main points and understandable word, picture,
The contents such as voice so that user need not download the main contents that whole section of video of viewing can just know monitoring video information, section
User time has been saved, information acquisition efficiency has been improve.
Here, it will be appreciated by those skilled in the art that the regular job of the noun of locality is binding operation person and user is practised
Used and Figure of description and set up, their appearance should not affect the protection domain of the application.
The application is described in detail above in association with accompanying drawing embodiment, those skilled in the art can be according to upper
State and bright many variations example is made to the application.Thus, some of embodiment details should not constitute the restriction to the application, this
Protection domain of the scope that application will be defined using appended claims as the application.
Claims (18)
1. a kind of video monitoring alarm method, wherein, including:
Obtain video content;
When suspicious content is included in the video content, export warning message, wherein, the warning message is included with regard to described
The summary info of suspicious content.
2. video monitoring alarm method according to claim 1, wherein, suspicious content is included in the video content
When, warning message is exported, including:
Detecting is moved to video content, the suspicious frame comprising moving object is extracted;
Generate and export warning message according to the suspicious frame comprising moving object.
3. video monitoring alarm method according to claim 2, wherein, according to the suspicious frame life comprising moving object
Into and export warning message, including:
Object identification is carried out to the moving object in the suspicious frame, the recognition result of the moving object is obtained;
Summary info with regard to the suspicious content is determined according to the recognition result of the moving object;
Generated according to the summary info with regard to the suspicious content and export warning message.
4. video monitoring alarm method according to claim 3, wherein, thing is carried out to the moving object in the suspicious frame
Body identification, including:
To filtering in the suspicious frame comprising easy flase drop content, the suspicious frame after filtering is obtained;
The moving object in suspicious frame after to the filtration carries out object identification.
5. video monitoring alarm method according to claim 4, wherein, the easy flase drop content includes:
The image change content caused by light change;
The image change content caused by predetermined movement object.
6. video monitoring alarm method according to claim 3, wherein, thing is carried out to the moving object in the suspicious frame
Body identification, including:
Using default object model, object identification is carried out to the moving object in the suspicious frame.
7. video monitoring alarm method according to claim 2, wherein, detecting is moved to video content, bag is extracted
Suspicious frame containing moving object, including:
Read the multiple successive image frames in video content;
Multiple successive image frames are carried out with the comparing calculation of interframe, the suspicious frame comprising moving object is extracted.
8. video monitoring alarm method according to claim 1, wherein, warning message is exported, including:
The warning message of output presets, wherein, the presets include following any one or more of combination:Text
Word, picture, voice and video.
9. video monitoring alarm method according to any one of claim 1 to 8, wherein, it is described with regard to described suspicious
The summary info of content includes the title of moving object, the time of occurrence of moving object, the sports immunology of moving object and motion
The sectional drawing of object.
10. a kind of Video Surveillance Alarm System, wherein, the Video Surveillance Alarm System includes:
Video capture device, for obtaining video content;
Analysis warning device, during for including suspicious content in the video content, exports warning message, wherein, the report
Alarming information includes the summary info with regard to the suspicious content.
11. Video Surveillance Alarm Systems according to claim 10, wherein, the analysis warning device, including:
Extraction element, for detecting is moved to video content, extracts the suspicious frame comprising moving object;
Alarm device, for generating and exporting warning message according to the suspicious frame comprising moving object.
12. Video Surveillance Alarm Systems according to claim 11, wherein, the alarm device, including:
Identification module, for object identification is carried out to the moving object in the suspicious frame, obtains the identification of the moving object
As a result;
Summary info determining module, for the summary with regard to the suspicious content is determined according to the recognition result of the moving object
Information;
Warning message generates output module, generates with regard to the summary info of the suspicious content for basis and exports alarm signal
Breath.
13. Video Surveillance Alarm Systems according to claim 12, wherein, the identification module is used for:
To filtering in the suspicious frame comprising easy flase drop content, the suspicious frame after filtering is obtained;
The moving object in suspicious frame after to the filtration carries out object identification.
14. Video Surveillance Alarm Systems according to claim 13, wherein, the easy flase drop content includes:
The image change content caused by light change;
The image change content caused by predetermined movement object.
15. Video Surveillance Alarm Systems according to claim 12, wherein, the identification module is used for:
Using default object model, object identification is carried out to the moving object in the suspicious frame.
16. Video Surveillance Alarm Systems according to claim 11, wherein, the extraction element is used for:
Read the multiple successive image frames in video content;
Multiple successive image frames are carried out with the comparing calculation of interframe, the suspicious frame comprising moving object is extracted.
17. Video Surveillance Alarm Systems according to claim 10, wherein, the warning message generates output module and uses
In:
The warning message of output presets, wherein, the presets include following any one or more of combination:Text
Word, picture, voice and video.
18. Video Surveillance Alarm Systems according to any one of claim 10 to 17, wherein, it is described with regard to it is described can
The summary info of doubtful content includes the title of moving object, the time of occurrence of moving object, the sports immunology of moving object and fortune
The sectional drawing of animal body.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710087254.5A CN106603999A (en) | 2017-02-17 | 2017-02-17 | Video monitoring alarming method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710087254.5A CN106603999A (en) | 2017-02-17 | 2017-02-17 | Video monitoring alarming method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106603999A true CN106603999A (en) | 2017-04-26 |
Family
ID=58587533
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710087254.5A Pending CN106603999A (en) | 2017-02-17 | 2017-02-17 | Video monitoring alarming method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106603999A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107845103A (en) * | 2017-10-23 | 2018-03-27 | 广东美的制冷设备有限公司 | Alarm method, device and computer-readable recording medium based on texture information |
CN107945437A (en) * | 2017-11-30 | 2018-04-20 | 深圳市龙之源科技股份有限公司 | Portable field Intelligent monitoring alarm device |
CN110012114A (en) * | 2019-05-05 | 2019-07-12 | 北京市众诚恒祥能源投资管理有限公司 | A kind of Environmental security early warning system based on Internet of Things |
CN110087030A (en) * | 2019-04-22 | 2019-08-02 | 北京宇视科技有限公司 | A kind of automatic alarm video monitoring equipment |
CN110225299A (en) * | 2019-05-06 | 2019-09-10 | 平安科技(深圳)有限公司 | Video monitoring method, device, computer equipment and storage medium |
CN110379108A (en) * | 2019-08-19 | 2019-10-25 | 铂纳思(东莞)高新科技投资有限公司 | A kind of method and its system of unmanned shop anti-thefting monitoring |
CN110517427A (en) * | 2018-05-22 | 2019-11-29 | 杭州萤石软件有限公司 | A kind of warning message recognition methods, server and system |
CN115830519A (en) * | 2023-03-01 | 2023-03-21 | 杭州遁甲科技有限公司 | Intelligent lock message reminding method |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104021570A (en) * | 2014-06-04 | 2014-09-03 | 电子科技大学 | Method for directional cross-border detection and mixing line detection in video |
CN104915655A (en) * | 2015-06-15 | 2015-09-16 | 西安电子科技大学 | Multi-path monitor video management method and device |
CN105046682A (en) * | 2015-05-20 | 2015-11-11 | 王向恒 | Video monitoring method based on local computing |
CN105046719A (en) * | 2015-07-03 | 2015-11-11 | 苏州科达科技股份有限公司 | Method and system for video monitoring |
CN105141885A (en) * | 2014-05-26 | 2015-12-09 | 杭州海康威视数字技术股份有限公司 | Method for video monitoring and device |
CN106060474A (en) * | 2016-06-27 | 2016-10-26 | 深圳辉锐天眼科技有限公司 | Method for upgrading traditional video surveillance to video early-warning system |
CN106210612A (en) * | 2015-04-30 | 2016-12-07 | 杭州海康威视数字技术股份有限公司 | Method for video coding, coding/decoding method and device thereof |
-
2017
- 2017-02-17 CN CN201710087254.5A patent/CN106603999A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105141885A (en) * | 2014-05-26 | 2015-12-09 | 杭州海康威视数字技术股份有限公司 | Method for video monitoring and device |
CN104021570A (en) * | 2014-06-04 | 2014-09-03 | 电子科技大学 | Method for directional cross-border detection and mixing line detection in video |
CN106210612A (en) * | 2015-04-30 | 2016-12-07 | 杭州海康威视数字技术股份有限公司 | Method for video coding, coding/decoding method and device thereof |
CN105046682A (en) * | 2015-05-20 | 2015-11-11 | 王向恒 | Video monitoring method based on local computing |
CN104915655A (en) * | 2015-06-15 | 2015-09-16 | 西安电子科技大学 | Multi-path monitor video management method and device |
CN105046719A (en) * | 2015-07-03 | 2015-11-11 | 苏州科达科技股份有限公司 | Method and system for video monitoring |
CN106060474A (en) * | 2016-06-27 | 2016-10-26 | 深圳辉锐天眼科技有限公司 | Method for upgrading traditional video surveillance to video early-warning system |
Non-Patent Citations (1)
Title |
---|
顾牧君: "《智能家居设计与施工》", 1 October 2004 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107845103A (en) * | 2017-10-23 | 2018-03-27 | 广东美的制冷设备有限公司 | Alarm method, device and computer-readable recording medium based on texture information |
CN107845103B (en) * | 2017-10-23 | 2022-03-11 | 广东美的制冷设备有限公司 | Alarm method and device based on texture information and computer readable storage medium |
CN107945437A (en) * | 2017-11-30 | 2018-04-20 | 深圳市龙之源科技股份有限公司 | Portable field Intelligent monitoring alarm device |
CN110517427A (en) * | 2018-05-22 | 2019-11-29 | 杭州萤石软件有限公司 | A kind of warning message recognition methods, server and system |
CN110087030A (en) * | 2019-04-22 | 2019-08-02 | 北京宇视科技有限公司 | A kind of automatic alarm video monitoring equipment |
CN110012114A (en) * | 2019-05-05 | 2019-07-12 | 北京市众诚恒祥能源投资管理有限公司 | A kind of Environmental security early warning system based on Internet of Things |
CN110012114B (en) * | 2019-05-05 | 2020-01-21 | 北京市众诚恒祥能源投资管理有限公司 | Environmental safety early warning system based on thing networking |
CN110225299A (en) * | 2019-05-06 | 2019-09-10 | 平安科技(深圳)有限公司 | Video monitoring method, device, computer equipment and storage medium |
CN110225299B (en) * | 2019-05-06 | 2022-03-04 | 平安科技(深圳)有限公司 | Video monitoring method and device, computer equipment and storage medium |
CN110379108A (en) * | 2019-08-19 | 2019-10-25 | 铂纳思(东莞)高新科技投资有限公司 | A kind of method and its system of unmanned shop anti-thefting monitoring |
CN115830519A (en) * | 2023-03-01 | 2023-03-21 | 杭州遁甲科技有限公司 | Intelligent lock message reminding method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106603999A (en) | Video monitoring alarming method and system | |
KR101897923B1 (en) | System for providing identify target object based on neural network learning model, method thereof, and computer readable storage having the same | |
CN109766779B (en) | Loitering person identification method and related product | |
CN110516609A (en) | A kind of fire video detection and method for early warning based on image multiple features fusion | |
KR101765722B1 (en) | System and method of generating narrative report based on cognitive computing for recognizing, tracking, searching and predicting vehicles and person attribute objects and events | |
US9001206B2 (en) | Cascadable camera tampering detection transceiver module | |
CN106408833A (en) | Perimeter intrusion detection method and system | |
CN111522987A (en) | Image auditing method and device and computer readable storage medium | |
KR102035592B1 (en) | A supporting system and method that assist partial inspections of suspicious objects in cctv video streams by using multi-level object recognition technology to reduce workload of human-eye based inspectors | |
CN109672863A (en) | A kind of construction personnel's safety equipment intelligent monitoring method based on image recognition | |
CN106412522A (en) | Video analysis detection method and system of object in indoor and outdoor environment | |
CN111405249A (en) | Monitoring method, monitoring device, server and computer-readable storage medium | |
CN107122743A (en) | Security-protecting and monitoring method, device and electronic equipment | |
CN111553305B (en) | System and method for identifying illegal videos | |
KR101084914B1 (en) | Indexing management system of vehicle-number and man-image | |
CN110188617A (en) | A kind of machine room intelligent monitoring method and system | |
CN111191498A (en) | Behavior recognition method and related product | |
CN111199172A (en) | Terminal screen recording-based processing method and device and storage medium | |
KR20120065817A (en) | Method and system for providing intelligent access monitoring, intelligent access monitoring apparatus, recording medium for intelligent access monitoring | |
CN113139452A (en) | Method for detecting behavior of using mobile phone based on target detection | |
CN115083229B (en) | Intelligent recognition and warning system of flight training equipment based on AI visual recognition | |
CN116419059A (en) | Automatic monitoring method, device, equipment and medium based on behavior label | |
CN115909144A (en) | Method and system for detecting abnormity of surveillance video based on counterstudy | |
CN113065482A (en) | Behavior detection method, system, computer device and medium based on image recognition | |
Vezzani et al. | Smoke detection in video surveillance: the use of visor (video surveillance on-line repository) |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170426 |
|
RJ01 | Rejection of invention patent application after publication |